On Fri, Jul 10, 2015 at 10:21 AM, Uros Bizjak <ubiz...@gmail.com> wrote:
> On Fri, Jul 10, 2015 at 7:10 PM, H.J. Lu <hjl.to...@gmail.com> wrote:
>> On Fri, Jul 10, 2015 at 9:30 AM, Uros Bizjak <ubiz...@gmail.com> wrote:
>>> On Thu, Jul 9, 2015 at 12:54 PM, H.J. Lu <hjl.to...@gmail.com> wrote:
>>>> Indirect sibcall with register arguments is OK when there is register
>>>> available for argument passing.
>>>>
>>>> OK for trunk if there is no regression?
>>>>
>>>>
>>>> H.J.
>>>> ---
>>>> gcc/
>>>>
>>>>         PR target/66819
>>>>         * config/i386/i386.c (ix86_function_ok_for_sibcall): Allow
>>>>         indirect sibcall with register arguments if register available
>>>>         for argument passing.
>>>>         (init_cumulative_args): Set cfun->machine->arg_reg_available_p
>>>>         to cum->nregs != 0.
>
> Please update the above entry for nregs > 0.
>
>>>>         (function_arg_advance_32): Set cfun->machine->arg_reg_available_p
>>>>         to 0 when setting cum->nregs = 0.
>>>
>>> Do we also need similar functionality for 64bit ABIs? What happens if
>>> we are out of argument regs there?
>>
>> 64-bit is OK since we have rax, r10 and r11 as scratch registers which
>> aren't used to pass arguments.
>
> Maybe this fact should be added as a comment in some appropriate place.
>
>>>>         * config/i386/i386.h (machine_function): Add arg_reg_available_p.
>>>>
>>>> gcc/testsuite/
>>>>
>>>>         PR target/66819
>>>>         * gcc.target/i386/pr66819-1.c: New test.
>>>>         * gcc.target/i386/pr66819-2.c: Likewise.
>>>>         * gcc.target/i386/pr66819-3.c: Likewise.
>>>>         * gcc.target/i386/pr66819-4.c: Likewise.
>>>>         * gcc.target/i386/pr66819-5.c: Likewise.
>>>> ---
>>>>  gcc/config/i386/i386.c                    | 15 +++++++++------
>>>>  gcc/config/i386/i386.h                    |  3 +++
>>>>  gcc/testsuite/gcc.target/i386/pr66819-1.c |  8 ++++++++
>>>>  gcc/testsuite/gcc.target/i386/pr66819-2.c |  8 ++++++++
>>>>  gcc/testsuite/gcc.target/i386/pr66819-3.c | 10 ++++++++++
>>>>  gcc/testsuite/gcc.target/i386/pr66819-4.c | 12 ++++++++++++
>>>>  gcc/testsuite/gcc.target/i386/pr66819-5.c | 10 ++++++++++
>>>>  7 files changed, 60 insertions(+), 6 deletions(-)
>>>>  create mode 100644 gcc/testsuite/gcc.target/i386/pr66819-1.c
>>>>  create mode 100644 gcc/testsuite/gcc.target/i386/pr66819-2.c
>>>>  create mode 100644 gcc/testsuite/gcc.target/i386/pr66819-3.c
>>>>  create mode 100644 gcc/testsuite/gcc.target/i386/pr66819-4.c
>>>>  create mode 100644 gcc/testsuite/gcc.target/i386/pr66819-5.c
>>>>
>>>> diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
>>>> index 54ee6f3..85e59a8 100644
>>>> --- a/gcc/config/i386/i386.c
>>>> +++ b/gcc/config/i386/i386.c
>>>> @@ -5628,12 +5628,12 @@ ix86_function_ok_for_sibcall (tree decl, tree exp)
>>>>        if (!decl
>>>>           || (TARGET_DLLIMPORT_DECL_ATTRIBUTES && DECL_DLLIMPORT_P (decl)))
>>>>         {
>>>> -         if (ix86_function_regparm (type, NULL) >= 3)
>>>> -           {
>>>> -             /* ??? Need to count the actual number of registers to be 
>>>> used,
>>>> -                not the possible number of registers.  Fix later.  */
>>>> -             return false;
>>>> -           }
>>>> +         /* FIXME: The symbol indirect call doesn't need a
>>>> +            call-clobbered register.  But we don't know if
>>>> +            this is a symbol indirect call or not  here.  */
>>>> +         if (ix86_function_regparm (type, NULL) >= 3
>>>> +             && !cfun->machine->arg_reg_available_p)
>>>
>>> Isn't enough to look at arg_reg_available here?
>>
>> We need to check ix86_function_regparm since nregs is 0 if
>> -mregparm=N isn't used and pr65753.c will fail.
>
> OK. Please add this comment, is not that obvious.
>
>>
>>>> +           return false;
>>>>         }
>>>>      }
>>>>
>>>> @@ -6567,6 +6567,7 @@ init_cumulative_args (CUMULATIVE_ARGS *cum,  /* 
>>>> Argument info to initialize */
>>>>                     ? X86_64_REGPARM_MAX
>>>>                     : X86_64_MS_REGPARM_MAX);
>>>>      }
>>>> +  cfun->machine->arg_reg_available_p = cum->nregs != 0;
>>>
>>> false instead of 0. This is a boolean.
>>
>> Updated.
>>
>>>>    if (TARGET_SSE)
>>>>      {
>>>>        cum->sse_nregs = SSE_REGPARM_MAX;
>>>> @@ -6636,6 +6637,7 @@ init_cumulative_args (CUMULATIVE_ARGS *cum,  /* 
>>>> Argument info to initialize */
>>>>           else
>>>>             cum->nregs = ix86_function_regparm (fntype, fndecl);
>>>>         }
>>>> +      cfun->machine->arg_reg_available_p = cum->nregs != 0;
>>>
>>> IMO, cum->nregs > 0 would be more descriptive.
>>
>> Updated.
>>
>>>>        /* Set up the number of SSE registers used for passing SFmode
>>>>          and DFmode arguments.  Warn for mismatching ABI.  */
>>>> @@ -7584,6 +7586,7 @@ pass_in_reg:
>>>>         {
>>>>           cum->nregs = 0;
>>>>           cum->regno = 0;
>>>> +         cfun->machine->arg_reg_available_p = 0;
>>>>         }
>>>>        break;
>>>>
>>>> diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
>>>> index 74334ff..0b6e304 100644
>>>> --- a/gcc/config/i386/i386.h
>>>> +++ b/gcc/config/i386/i386.h
>>>> @@ -2479,6 +2479,9 @@ struct GTY(()) machine_function {
>>>>    /* If true, it is safe to not save/restore DRAP register.  */
>>>>    BOOL_BITFIELD no_drap_save_restore : 1;
>>>>
>>>> +  /* If true, there is register available for argument passing.  */
>>>> +  BOOL_BITFIELD arg_reg_available_p : 1;
>>>
>>> This is not a predicate, but a boolean flag. Please remove _p from the name.
>>
>> Updated.
>>
>> Here is the updated patch.  OK for trunk?
>
> OK with a small comment additions.
>
> +  /* If true, there is register available for argument passing.  */
> +  BOOL_BITFIELD arg_reg_available : 1;
> +
>
> Please mention here that this is for 32bit targets only.
>

Updated. Is this one OK?

Thanks.


-- 
H.J.
From 528ddcbfa2d66c6b34dea88d9ad64593be89159e Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.to...@gmail.com>
Date: Wed, 8 Jul 2015 21:10:25 -0700
Subject: [PATCH] Allow indirect sibcall with register arguments

Indirect sibcall with register arguments is OK when there is register
available for argument passing.

gcc/

	PR target/66819
	* config/i386/i386.c (ix86_function_ok_for_sibcall): Allow
	indirect sibcall with register arguments if register available
	for argument passing.
	(init_cumulative_args): Set cfun->machine->arg_reg_available
	to (cum->nregs > 0) or to true if function has a variable
	argument list.
	(function_arg_advance_32): Set cfun->machine->arg_reg_available
	to false if cum->nregs <= 0.
	* config/i386/i386.h (machine_function): Add arg_reg_available.

gcc/testsuite/

	PR target/66819
	* gcc.target/i386/pr66819-1.c: New test.
	* gcc.target/i386/pr66819-2.c: Likewise.
	* gcc.target/i386/pr66819-3.c: Likewise.
	* gcc.target/i386/pr66819-4.c: Likewise.
	* gcc.target/i386/pr66819-5.c: Likewise.
---
 gcc/config/i386/i386.c                    | 23 +++++++++++++++++------
 gcc/config/i386/i386.h                    |  7 +++++++
 gcc/testsuite/gcc.target/i386/pr66819-1.c |  8 ++++++++
 gcc/testsuite/gcc.target/i386/pr66819-2.c |  8 ++++++++
 gcc/testsuite/gcc.target/i386/pr66819-3.c | 10 ++++++++++
 gcc/testsuite/gcc.target/i386/pr66819-4.c | 12 ++++++++++++
 gcc/testsuite/gcc.target/i386/pr66819-5.c | 10 ++++++++++
 7 files changed, 72 insertions(+), 6 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr66819-1.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr66819-2.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr66819-3.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr66819-4.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr66819-5.c

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 6929caf..0f96452 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -5629,12 +5629,16 @@ ix86_function_ok_for_sibcall (tree decl, tree exp)
       if (!decl
 	  || (TARGET_DLLIMPORT_DECL_ATTRIBUTES && DECL_DLLIMPORT_P (decl)))
 	{
-	  if (ix86_function_regparm (type, NULL) >= 3)
-	    {
-	      /* ??? Need to count the actual number of registers to be used,
-		 not the possible number of registers.  Fix later.  */
-	      return false;
-	    }
+	  /* Check if regparm >= 3 since arg_reg_available is set to
+	     false if regparm == 0.  If regparm is 1 or 2, there is
+	     always a call-clobbered register available.
+
+	     ??? The symbol indirect call doesn't need a call-clobbered
+	     register.  But we don't know if this is a symbol indirect
+	     call or not here.  */
+	  if (ix86_function_regparm (type, NULL) >= 3
+	      && !cfun->machine->arg_reg_available)
+	    return false;
 	}
     }
 
@@ -6610,6 +6614,10 @@ init_cumulative_args (CUMULATIVE_ARGS *cum,  /* Argument info to initialize */
       if (stdarg_p (fntype))
 	{
 	  cum->nregs = 0;
+	  /* Since in 32-bit, variable arguments are always passed on
+	     stack, there is scratch register available for indirect
+	     sibcall.  */
+	  cfun->machine->arg_reg_available = true;
 	  cum->sse_nregs = 0;
 	  cum->mmx_nregs = 0;
 	  cum->warn_avx512f = false;
@@ -6642,6 +6650,8 @@ init_cumulative_args (CUMULATIVE_ARGS *cum,  /* Argument info to initialize */
 	 and DFmode arguments.  Warn for mismatching ABI.  */
       cum->float_in_sse = ix86_function_sseregparm (fntype, fndecl, true);
     }
+
+  cfun->machine->arg_reg_available = (cum->nregs > 0);
 }
 
 /* Return the "natural" mode for TYPE.  In most cases, this is just TYPE_MODE.
@@ -7584,6 +7594,7 @@ pass_in_reg:
       if (cum->nregs <= 0)
 	{
 	  cum->nregs = 0;
+	  cfun->machine->arg_reg_available = false;
 	  cum->regno = 0;
 	}
       break;
diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index 74334ff..0fcf391 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -2479,6 +2479,13 @@ struct GTY(()) machine_function {
   /* If true, it is safe to not save/restore DRAP register.  */
   BOOL_BITFIELD no_drap_save_restore : 1;
 
+  /* If true, there is register available for argument passing.  This
+     is used only in ix86_function_ok_for_sibcall by 32-bit to determine
+     if there is scratch register available for indirect sibcall.  In
+     64-bit, rax, r10 and r11 are scratch registers which aren't used to
+     pass arguments and can be used for indirect sibcall.  */
+  BOOL_BITFIELD arg_reg_available : 1;
+
   /* During prologue/epilogue generation, the current frame state.
      Otherwise, the frame state at the end of the prologue.  */
   struct machine_frame_state fs;
diff --git a/gcc/testsuite/gcc.target/i386/pr66819-1.c b/gcc/testsuite/gcc.target/i386/pr66819-1.c
new file mode 100644
index 0000000..7c8a1ab
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr66819-1.c
@@ -0,0 +1,8 @@
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-O2 -mregparm=3" } */
+/* { dg-final { scan-assembler-not "call" } } */
+
+void foo(void (*bar)(void))
+{
+  bar();
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr66819-2.c b/gcc/testsuite/gcc.target/i386/pr66819-2.c
new file mode 100644
index 0000000..9de4f97
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr66819-2.c
@@ -0,0 +1,8 @@
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-fPIC -O2 -mregparm=3" } */
+/* { dg-final { scan-assembler-not "call" } } */
+
+void foo(void (*bar)(void))
+{
+  bar();
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr66819-3.c b/gcc/testsuite/gcc.target/i386/pr66819-3.c
new file mode 100644
index 0000000..3bc5a34
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr66819-3.c
@@ -0,0 +1,10 @@
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-O2 -mregparm=3" } */
+/* { dg-final { scan-assembler-not "call" } } */
+
+void (*bar)(int, int);
+
+void foo(int i, int j)
+{
+  bar(i, j);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr66819-4.c b/gcc/testsuite/gcc.target/i386/pr66819-4.c
new file mode 100644
index 0000000..18b2ccf
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr66819-4.c
@@ -0,0 +1,12 @@
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-O2 -mregparm=3" } */
+/* { dg-final { scan-assembler-not "call" } } */
+
+#include <stdarg.h>
+
+void (*bar)(int, va_list); 
+
+void foo(int i, va_list args)
+{
+  bar(i, args);
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr66819-5.c b/gcc/testsuite/gcc.target/i386/pr66819-5.c
new file mode 100644
index 0000000..6b019d1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr66819-5.c
@@ -0,0 +1,10 @@
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-O2 -mregparm=3" } */
+/* { dg-final { scan-assembler "call" } } */
+
+void (*bar)(int, int, int);
+
+void foo(int i, int j, int k)
+{
+  bar(i, j, k);
+}
-- 
2.4.3

Reply via email to